bloomz-3B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1200 ± 16, rank #9622 of 10916 rated models, from 86 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Physics | 35.1 | Accuracy (%) | 82 |
| CARTE - Pays de la Loire | 47.4 | Accuracy (%) on the 133 CARTE questions about Pays de la Loi | 63.5 |
| CARTE - Auvergne-Rhone-Alpes | 51.4 | Accuracy (%) on the 208 CARTE questions about Auvergne-Rhone | 61.5 |
| CARTE - Normandie | 55.8 | Accuracy (%) on the 156 CARTE questions about Normandie, 0-s | 59.6 |
| CARTE - Bourgogne-Franche-Comte | 54.9 | Accuracy (%) on the 203 CARTE questions about Bourgogne-Fran | 57.7 |
| CARTE - Centre-Val de Loire | 48.5 | Accuracy (%) on the 136 CARTE questions about Centre-Val de | 57.7 |
| CARTE - Occitanie | 51.8 | Accuracy (%) on the 139 CARTE questions about Occitanie, 0-s | 57.7 |
| CARTE-LV | 52.8 | Accuracy (%) on the 233 CARTE-LV questions on regional lingu | 57.7 |
| MMLU-by-task - Machine Learning | 33.93 | Accuracy (%) | 57.4 |
| MMLU-by-task - Moral Scenarios | 26.82 | Accuracy (%) | 56.5 |
| CARTE - Corse | 67 | Accuracy (%) on the 100 CARTE questions about Corse (Corsica | 55.8 |
| CARTE | 53.2 | Accuracy (%) on all 2,431 CARTE questions (question-weighted | 53.8 |
Interactive version: theaggregate.ai/model?slug=bloomz-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.